Papers › Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

1 Oct 2024arXiv:2410.00418archive 2025-07-28

Guy Ohayon, Tomer Michaeli, Michael Elad

Photo-realistic image restoration algorithms are typically evaluated by distortion measures (e.g., PSNR, SSIM) and by perceptual quality measures (e.g., FID, NIQE), where the desire is to attain the lowest possible distortion without compromising on perceptual quality. To achieve this goal, current methods commonly attempt to sample from the posterior distribution, or to optimize a weighted sum of a distortion loss (e.g., MSE) and a perceptual quality loss (e.g., GAN). Unlike previous works, this paper is concerned specifically with the optimal estimator that minimizes the MSE under a constraint of perfect perceptual index, namely where the distribution of the reconstructed images is equal to that of the ground-truth ones. A recent theoretical result shows that such an estimator can be constructed by optimally transporting the posterior mean prediction (MMSE estimate) to the distribution of the ground-truth images. Inspired by this result, we introduce Posterior-Mean Rectified Flow (PMRF), a simple yet highly effective algorithm that approximates this optimal estimator. In particular, PMRF first predicts the posterior mean, and then transports the result to a high-quality image using a rectified flow model that approximates the desired optimal transport map. We investigate the theoretical utility of PMRF and demonstrate that it consistently outperforms previous methods on a variety of image restoration tasks.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 7 ran (3 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ohayonguy/PMRF officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 7 ran (4 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
2ran; the contract check could not run
1ran
3unverified

Licence: 4 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ohayonguy/PMRF. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ohayonguy/PMRF official repository 10 samples, 7 ran (4 instrument-failed) · 3 unverified
calculate_points evaluation/calculate_landmark_distance.py ran; the contract check could not run (RAISES) MIT (permissive) · 236cf18a7e5a0db9 · report fixture: returned ndarray · level recorded 2026-09-24
conv3x3 in 1,376 papers evaluation/awing_arch.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · cd28335574411d48 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, strd:int/0/int, padding:int/0/int, bias:bool/0/bool, dilation:int/0/int · returned Conv2d · level recorded 2026-09-22
img2tensor in 7 papers evaluation/calculate_cos_dist.py ran MIT (permissive) · 8b5cf3d00508f17b · report fixture: signature imgs:ndarray/3/int, bgr2rgb:bool/0/bool, float32:bool/0/bool · returned Tensor · level recorded 2026-09-24
load_image_torch evaluation/calculate_cos_dist.py ran · honoured contract MIT (permissive) · 6d7e52beb54f602e · report fixture: signature img_path:str/0/str · returned Tensor · level recorded 2026-09-24
mesh_grid in 12 papers utils/basicsr_custom.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 794d4f7fc184e7e5 · report fixture: signature kernel_size:int/0/int · returned tuple · level recorded 2026-09-26
pdf2 in 9 papers utils/basicsr_custom.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 321b9c73d589eb9e · report fixture: signature sigma_matrix:ndarray/2/float, grid:ndarray/3/float · returned ndarray · level recorded 2026-09-26
sigma_matrix2 in 9 papers utils/basicsr_custom.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · e3444ff2b9d24600 · report fixture: signature sig_x:float/0/float, sig_y:float/0/float, theta:float/0/float · returned ndarray · level recorded 2026-09-26
calculate_points evaluation/awing_arch.py unverified MIT (permissive) · 37e244c7bbaccec7 · report
init_alignment_model evaluation/calculate_landmark_distance.py unverified MIT (permissive) · 60130eacf5484058 · report
load_image in 273 papers evaluation/calculate_cos_dist.py unverified MIT (permissive) · d8d6d771a1dadff4 · report

Tasks

Blind Face RestorationImage ColorizationImage DenoisingImage InpaintingImage RestorationImage Super-ResolutionSSIM

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Blind Face Restoration CelebA-Test PMRF Deg. 30.67 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF FID 37.46 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF NIQE 4.118 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF PSNR 26.37 #15 of 15 Archive leaderboard report
Blind Face Restoration CelebA-Test PMRF SSIM 0.7073 #15 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections